{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:MWLCA5HLHLDROLZZSQ6C7MV5DU","short_pith_number":"pith:MWLCA5HL","canonical_record":{"source":{"id":"2107.02278","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-05T21:24:02Z","cross_cats_sorted":["cs.CY","cs.SI"],"title_canon_sha256":"d1451c224029be51ecd6c7d976afa9e166b9ac6821d594db556713d31d94ddc6","abstract_canon_sha256":"d347c7f706d68cb98ef5b4333d23e60fae51d9e85798e6f53d29ced7ae48a166"},"schema_version":"1.0"},"canonical_sha256":"65962074eb3ac7172f39943c2fb2bd1d09f74d453d7aa822407dbea784671bed","source":{"kind":"arxiv","id":"2107.02278","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.02278","created_at":"2026-07-05T02:55:18Z"},{"alias_kind":"arxiv_version","alias_value":"2107.02278v1","created_at":"2026-07-05T02:55:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.02278","created_at":"2026-07-05T02:55:18Z"},{"alias_kind":"pith_short_12","alias_value":"MWLCA5HLHLDR","created_at":"2026-07-05T02:55:18Z"},{"alias_kind":"pith_short_16","alias_value":"MWLCA5HLHLDROLZZ","created_at":"2026-07-05T02:55:18Z"},{"alias_kind":"pith_short_8","alias_value":"MWLCA5HL","created_at":"2026-07-05T02:55:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:MWLCA5HLHLDROLZZSQ6C7MV5DU","target":"record","payload":{"canonical_record":{"source":{"id":"2107.02278","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-05T21:24:02Z","cross_cats_sorted":["cs.CY","cs.SI"],"title_canon_sha256":"d1451c224029be51ecd6c7d976afa9e166b9ac6821d594db556713d31d94ddc6","abstract_canon_sha256":"d347c7f706d68cb98ef5b4333d23e60fae51d9e85798e6f53d29ced7ae48a166"},"schema_version":"1.0"},"canonical_sha256":"65962074eb3ac7172f39943c2fb2bd1d09f74d453d7aa822407dbea784671bed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:55:18.745660Z","signature_b64":"yklowAm66Z+DiSy5Sq4d2BgVVA73gCczAvp626T/CSX+kOGIgL2FumKnxWayL6VMH7vo7RV6C1AkFB1X2aPfCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65962074eb3ac7172f39943c2fb2bd1d09f74d453d7aa822407dbea784671bed","last_reissued_at":"2026-07-05T02:55:18.745119Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:55:18.745119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.02278","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:55:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k4XNKSwUHaUi2/mGWmXag1tV9ajQzryZJioALNPjSIztBABcQsDIIt8CUc3BefuQSil0Jx6lVyEayLCJyCppCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:49:35.801902Z"},"content_sha256":"374f2275ea467bdf45b443f2364973671d775b502fd909d7194e21bbaee7d8bc","schema_version":"1.0","event_id":"sha256:374f2275ea467bdf45b443f2364973671d775b502fd909d7194e21bbaee7d8bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:MWLCA5HLHLDROLZZSQ6C7MV5DU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"\"Garbage In, Garbage Out\" Revisited: What Do Machine Learning Application Papers Report About Human-Labeled Training Data?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY","cs.SI"],"primary_cat":"cs.LG","authors_text":"Aayush Shah, Dominique Cope, Jamie Ip, Jenny Weng, Marsha Lotosh, Rebekah Tang, R. Stuart Geiger","submitted_at":"2021-07-05T21:24:02Z","abstract_excerpt":"Supervised machine learning, in which models are automatically derived from labeled training data, is only as good as the quality of that data. This study builds on prior work that investigated to what extent 'best practices' around labeling training data were followed in applied ML publications within a single domain (social media platforms). In this paper, we expand by studying publications that apply supervised ML in a far broader spectrum of disciplines, focusing on human-labeled data. We report to what extent a random sample of ML application papers across disciplines give specific detail"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.02278","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2107.02278/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:55:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tFguuJy+dL9kkIn+GpkkOFOsZ9GtiffVHaMO6zvcXeY0+0fxHwwO+ZlxYV1Xm6v+WOBYmJgWekmzyeQZCkxvCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:49:35.802296Z"},"content_sha256":"8335e26657bdbad4effe294327822e3df76e345a4216f58248fdb4628a8ff26d","schema_version":"1.0","event_id":"sha256:8335e26657bdbad4effe294327822e3df76e345a4216f58248fdb4628a8ff26d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MWLCA5HLHLDROLZZSQ6C7MV5DU/bundle.json","state_url":"https://pith.science/pith/MWLCA5HLHLDROLZZSQ6C7MV5DU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MWLCA5HLHLDROLZZSQ6C7MV5DU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T17:49:35Z","links":{"resolver":"https://pith.science/pith/MWLCA5HLHLDROLZZSQ6C7MV5DU","bundle":"https://pith.science/pith/MWLCA5HLHLDROLZZSQ6C7MV5DU/bundle.json","state":"https://pith.science/pith/MWLCA5HLHLDROLZZSQ6C7MV5DU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MWLCA5HLHLDROLZZSQ6C7MV5DU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MWLCA5HLHLDROLZZSQ6C7MV5DU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d347c7f706d68cb98ef5b4333d23e60fae51d9e85798e6f53d29ced7ae48a166","cross_cats_sorted":["cs.CY","cs.SI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-05T21:24:02Z","title_canon_sha256":"d1451c224029be51ecd6c7d976afa9e166b9ac6821d594db556713d31d94ddc6"},"schema_version":"1.0","source":{"id":"2107.02278","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.02278","created_at":"2026-07-05T02:55:18Z"},{"alias_kind":"arxiv_version","alias_value":"2107.02278v1","created_at":"2026-07-05T02:55:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.02278","created_at":"2026-07-05T02:55:18Z"},{"alias_kind":"pith_short_12","alias_value":"MWLCA5HLHLDR","created_at":"2026-07-05T02:55:18Z"},{"alias_kind":"pith_short_16","alias_value":"MWLCA5HLHLDROLZZ","created_at":"2026-07-05T02:55:18Z"},{"alias_kind":"pith_short_8","alias_value":"MWLCA5HL","created_at":"2026-07-05T02:55:18Z"}],"graph_snapshots":[{"event_id":"sha256:8335e26657bdbad4effe294327822e3df76e345a4216f58248fdb4628a8ff26d","target":"graph","created_at":"2026-07-05T02:55:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2107.02278/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Supervised machine learning, in which models are automatically derived from labeled training data, is only as good as the quality of that data. This study builds on prior work that investigated to what extent 'best practices' around labeling training data were followed in applied ML publications within a single domain (social media platforms). In this paper, we expand by studying publications that apply supervised ML in a far broader spectrum of disciplines, focusing on human-labeled data. We report to what extent a random sample of ML application papers across disciplines give specific detail","authors_text":"Aayush Shah, Dominique Cope, Jamie Ip, Jenny Weng, Marsha Lotosh, Rebekah Tang, R. Stuart Geiger","cross_cats":["cs.CY","cs.SI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-05T21:24:02Z","title":"\"Garbage In, Garbage Out\" Revisited: What Do Machine Learning Application Papers Report About Human-Labeled Training Data?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.02278","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:374f2275ea467bdf45b443f2364973671d775b502fd909d7194e21bbaee7d8bc","target":"record","created_at":"2026-07-05T02:55:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d347c7f706d68cb98ef5b4333d23e60fae51d9e85798e6f53d29ced7ae48a166","cross_cats_sorted":["cs.CY","cs.SI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-05T21:24:02Z","title_canon_sha256":"d1451c224029be51ecd6c7d976afa9e166b9ac6821d594db556713d31d94ddc6"},"schema_version":"1.0","source":{"id":"2107.02278","kind":"arxiv","version":1}},"canonical_sha256":"65962074eb3ac7172f39943c2fb2bd1d09f74d453d7aa822407dbea784671bed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65962074eb3ac7172f39943c2fb2bd1d09f74d453d7aa822407dbea784671bed","first_computed_at":"2026-07-05T02:55:18.745119Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:55:18.745119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yklowAm66Z+DiSy5Sq4d2BgVVA73gCczAvp626T/CSX+kOGIgL2FumKnxWayL6VMH7vo7RV6C1AkFB1X2aPfCg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:55:18.745660Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.02278","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:374f2275ea467bdf45b443f2364973671d775b502fd909d7194e21bbaee7d8bc","sha256:8335e26657bdbad4effe294327822e3df76e345a4216f58248fdb4628a8ff26d"],"state_sha256":"6ec56f55a99a23404f2c3ce17c9bfea90874f224c49fd465fa092f7a1dbc264e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N7WDvpEz/Gj3mbOU+jMu55cVJ1ngsAZgMC7AtroppDYHo9HSFVvLsXHocn+MMsCPbaQGCGBaC59KAJ4DJ/nhAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T17:49:35.805317Z","bundle_sha256":"68e35acca0d3d749bd01dde3840afef40bdf4e60913ec6093e966496f11bee64"}}